llms.txt Generator
Create an llms.txt file from your sitemap or URL list, grouped into sections with titles, then validate any llms.txt line by line against the llmstxt.org format.
The interactive tool loads here when JavaScript runs.
About this toolWhat is the llms.txt Generator?
Paste your sitemap.xml or a list of URLs and this generator groups the pages into sections by path, gives each link a readable title from its slug and builds an llms.txt in the format described on llmstxt.org: an H1 with the site name, a blockquote summary, optional details, H2 sections of links, and an Optional section for material a reader can skip. Edit titles, add notes, move links between sections and download the file.
The second mode checks an existing llms.txt and reports problems by line number: a missing H1, a second H1, list items without a Markdown link, prose inside link sections, deeper headings, relative URLs and duplicates. Everything runs in your browser.
- Imports sitemap.xml or plain URL lists
- Groups by path and titles pages from their slugs
- Editable sections, notes and an Optional section
- Line-by-line validator for existing files
- Download as llms.txt
- Runs fully in the browser
Updated
How to use the llms.txt Generator
- Paste a sitemap.xml or one URL per line and press Group into sections.
- Enter the site name for the H1 and a one or two sentence summary with the facts a reader most needs.
- Rename sections, fix titles and add short notes that say what each page answers.
- Move secondary links (blog posts, changelogs, legal pages) to Optional.
- Download llms.txt and publish it at the root of your site, or at a subpath for a docs section.
- Use Check an existing file to validate an llms.txt you already have.
Worked examples
Docs site from a sitemap
Input
10 URLs under /docs, /api, /blog and /changelog
Output
Sections Pages, Docs and API; blog and changelog links under Optional
Grouping by the first path segment matches how most documentation sites are organised.
Validation
Input
A file whose first line is "Welcome to our docs!" and whose links are "- Quickstart: https://..."
Output
Error on line 1 (must start with an H1) and errors on each list item without a Markdown link
Agents that parse llms.txt expect the link list pattern; plain URLs are easy to miss.
Background and insight
llms.txt was proposed by Jeremy Howard of Answer.AI in 2024 as a small Markdown file at a site's root that tells language models and agents what the site is and where its most useful pages are, in a form that fits in a context window. The only required part is the H1. Then come an optional blockquote summary, optional details in any Markdown except headings, and H2 sections whose lists use the pattern "- [title](url): notes". A section called Optional marks links that can be skipped when context is short. The proposal also suggests offering a Markdown copy of pages at the same URL with .md appended.
llms-full.txt is a separate convention that grew up around the proposal: one file with the full text of the linked pages. It is useful for documentation sites that want coding assistants to load everything in one fetch. Neither file is a crawling standard: no major AI search engine has said it ranks or cites pages because of llms.txt, so treat it as a cheap addition alongside robots.txt, a sitemap and server-rendered pages, not a replacement for them.
Common use cases
Developer documentation
Point coding assistants at the quick start, auth guide and API reference first.
SaaS marketing sites
Summarise the product, pricing and key help pages in one file.
Checking a vendor's file
Validate an llms.txt before you rely on it in your own agent.
Large sites
Publish a separate llms.txt per section, such as /docs/llms.txt, so each stays short.
Tips and limitations
- Keep it short. The point is a curated map, not a copy of the sitemap.
- Write notes that say what a page answers ("rate limits per plan"), not marketing copy.
- Use absolute URLs so the file works when read on its own.
- Generate it at build time from the same source as your sitemap so it never goes stale.
- If you publish llms-full.txt, keep it in sync too; outdated full text is worse than none.
Frequently asked questions
What is llms.txt?
A Markdown file, usually at /llms.txt, that summarises a site and links its most useful pages for language models and agents. It was proposed at llmstxt.org in 2024.
What must an llms.txt contain?
Only an H1 with the site or project name is required. A blockquote summary, details and H2 sections of "- [title](url): notes" links are optional but expected.
Do ChatGPT or Google use llms.txt?
None of the major AI search engines has said it uses llms.txt for ranking or citations. Some coding assistants and agent tools read it when it exists, which is why it is still worth a few minutes.
What goes in the Optional section of llms.txt?
Links a reader can skip when context is short, such as blog posts, changelogs and background material.
What is llms-full.txt?
A companion convention: one file with the full Markdown text of the linked pages, so a tool can load everything in one request. It is not part of the core llms.txt format.
Can I have more than one llms.txt?
Yes. The proposal allows files at subpaths such as /docs/llms.txt, covering the pages under that path; the most specific file applies.
Is there an in-depth guide to the llms.txt Generator?
Yes. “How to Make Your Website Visible to AI Assistants and AI Search” covers the background, how it works, common pitfalls and worked examples. Read the full guide.
Related Tools You May Like
Free, in-browser tools that pair well with this one.